Surrogate models based on machine learning methods for parameter estimation of left ventricular myocardium.

Surrogate models based on machine learning methods for parameter estimation of left ventricular myocardium.
复制标题

基于机器学习方法的左心室心肌参数估计替代模型

DOI:
10.1098/rsos.201121
复制
发表时间:
2021-01
影响因子:
3.5
通讯作者:
Gao H
Gao H
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Cai L;Ren L;Wang Y;Xie W;Zhu G;Gao H

文献摘要

参考文献

被引文献

相似文献

生物力学研究前沿的一个长期存在的问题是开发能够从临床数据估计材料特性的快速方法。在本文中,我们研究了三个代理模型的基础上,机器学习(ML)方法的快速参数估计的左心室(LV)心肌。我们使用三种ML方法K-最近邻(KNN),XGBoost和多层感知器(MLP)来模拟舒张期充盈期间压力和容积应变之间的关系。首先,为了训练代理模型,使用LV舒张充盈的前向有限元模拟器。然后将训练数据投影到低维参数化空间中。接下来,训练三个ML模型来学习压力-体积和压力-应变的关系。最后,利用这些训练好的代理模型,构造了一个逆参数估计问题。结果表明,这三种ML模型都能很好地学习压力-体积和压力-应变关系,并且使用代理模型进行参数推断可以在几分钟内完成。与KNN模型相比,XGBoost和MLP模型的估计参数具有更小的不确定性。我们的研究结果进一步表明,XGBoost模型是更好地预测左室舒张动力学和估计被动参数比其他两个代理模型。进一步的研究是必要的,以调查如何XGBoost可以用于模拟心脏泵功能在多物理和多尺度的框架。
A long-standing problem at the frontier of biomechanical studies is to develop fast methods capable of estimating material properties from clinical data. In this paper, we have studied three surrogate models based on machine learning (ML) methods for fast parameter estimation of left ventricular (LV) myocardium. We use three ML methods named K-nearest neighbour (KNN), XGBoost and multi-layer perceptron (MLP) to emulate the relationships between pressure and volume strains during the diastolic filling. Firstly, to train the surrogate models, a forward finite-element simulator of LV diastolic filling is used. Then the training data are projected in a low-dimensional parametrized space. Next, three ML models are trained to learn the relationships of pressure–volume and pressure–strain. Finally, an inverse parameter estimation problem is formulated by using those trained surrogate models. Our results show that the three ML models can learn the relationships of pressure–volume and pressure–strain very well, and the parameter inference using the surrogate models can be carried out in minutes. Estimated parameters from both the XGBoost and MLP models have much less uncertainties compared with the KNN model. Our results further suggest that the XGBoost model is better for predicting the LV diastolic dynamics and estimating passive parameters than other two surrogate models. Further studies are warranted to investigate how XGBoost can be used for emulating cardiac pump function in a multi-physics and multi-scale framework.
DOI: 10.1002/cnm.2652
发表时间: 2014-11
影响因子: 2.1
作者:
Gao H;Wang H;Berry C;Luo X;Griffith BE
通讯作者: Griffith BE
DOI: 10.1098/rsif.2017.0203
发表时间: 2017-07
期刊: Journal of the Royal Society, Interface
影响因子: --
作者:
Gao H;Aderhold A;Mangion K;Luo X;Husmeier D;Berry C
通讯作者: Berry C
DOI: 10.3389/fphy.2019.00117
发表时间: 2019-09-06
影响因子: 3.1
作者:
Dabiri, Yaghoub;Van der Velden, Alex;Guccione, Julius M.
通讯作者: Guccione, Julius M.
DOI: 10.1214/aos/1013203451
发表时间: 2001-10-01
影响因子: 4.5
作者:
Friedman, JH
通讯作者: Friedman, JH
DOI: 10.1002/cnm.2982
发表时间: 2018-07
影响因子: 2.1
作者:
Finsberg H;Xi C;Tan JL;Zhong L;Genet M;Sundnes J;Lee LC;Wall ST
通讯作者: Wall ST